robust-llm-wiki: Instructions file for Claude Code

CLAUDE.md

robust-llm-wiki CLAUDE.md is an instructions file for Claude Code from KevinYoung-Kw/robust-llm-wiki. It costs 514 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for a knowledge wiki based on raw sources, maintained pages, and operating rules. It explains how an agent should ingest sources, update pages, search the wiki, and record operations.

In plain words
What is it for?
Use it when working in the robust-llm-wiki repository. It guides source summaries, related-page updates, index maintenance, logs, and queries.
Why use it?
It gives the agent project-specific rules for preserving source material and keeping the knowledge base organized.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is KevinYoung-Kw/robust-llm-wiki's own configuration. It tells Claude Code how to work on robust-llm-wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything robust-llm-wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to KevinYoung-Kw/robust-llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/KevinYoung-Kw/robust-llm-wiki/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/KevinYoung-Kw/robust-llm-wiki

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for robust-llm-wiki CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kevinyoung-kw/robust-llm-wiki/claude-md/github.svg)](https://agentmods.dev/instructions/kevinyoung-kw/robust-llm-wiki/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kevinyoung-kw/robust-llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinyoung-kw/robust-llm-wiki/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for robust-llm-wiki CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kevinyoung-kw/robust-llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinyoung-kw/robust-llm-wiki/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 514 This file is loaded in full into every session.
When invoked 514 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00514 $0.00514
Opus 5 $0.00257 $0.00257
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00051 $0.00051

Measured 11d ago against content hash 7819bfae455a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

robust-llm-wiki CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This repository is about Karpathy-style LLM-Wiki as an operating pattern, not just as a slogan.

If you only read one file, start here and then continue to:

  1. schema/robust-llm-wiki-CLAUDE.md
  2. schema/SPEC.md

The Original Karpathy Baseline, Made Explicit

Do not reduce the original pattern to a vague sentence like "preserve the kernel."

The concrete baseline is:

  1. There are three layers: raw sources, wiki, and schema.
  2. raw sources are immutable. Read them, cite them, synthesize from them, but do not rewrite them.
  3. wiki is the maintained markdown knowledge base. The agent is expected to write and maintain this layer.
  4. schema is the contract that teaches the agent how to operate the wiki safely.

The original workflow is also concrete:

  1. ingest reads a new source,
  2. writes or updates a source summary page,
  3. updates related entity, concept, comparison, overview, or synthesis pages,
  4. updates index.md,
  5. appends an operation entry to log.md.

The original query behavior is:

  1. search the wiki first,
  2. often read index.md first,
  3. drill into relevant pages,
  4. synthesize an answer from maintained wiki pages,
  5. optionally file valuable answer artifacts back into the wiki.

The original lint behavior is:

  1. check contradictions across pages,
  2. look for stale claims superseded by newer sources,
  3. find orphan pages or weak cross-references,
  4. spot important concepts that should exist as pages but do not yet,
  5. propose concrete maintenance actions.

index.md and log.md are not decoration in this pattern.

  1. index.md is the content catalog and first navigation surface.
  2. log.md is the append-only operational timeline.

If an agent ignores all of that and only remembers "wiki + links + ingest/query/lint", it has not actually understood the Karpathy baseline.

Repository-Specific Policy

After loading this file, follow the full operator policy in schema/robust-llm-wiki-CLAUDE.md.

That file defines:

Read the full file on GitHub · 64 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 64 lines · 514 tokens per session scan A 7819bfae455a

Subscribe to this mod's changes

robust-llm-wiki CLAUDE.md is an instructions file published in the GitHub repository KevinYoung-Kw/robust-llm-wiki (10 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 514 tokens to every session, about $0.0026 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens